Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3867 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3323. Min Act: -0.0000

Data Index: 1461362 (The Pile)

Max Activating Token Index: 328

Text #1

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3372. Min Act: -0.0000

Data Index: 1180077 (The Pile)

Max Activating Token Index: 235

Text #2

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3345. Min Act: -0.0000

Data Index: 626312 (The Pile)

Max Activating Token Index: 254

Text #3

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3113. Min Act: -0.0000

Data Index: 828424 (The Pile)

Max Activating Token Index: 791

Text #4

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3223. Min Act: -0.0000

Data Index: 821569 (The Pile)

Max Activating Token Index: 368

Text #5

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1033096 (The Pile)

Max Activating Token Index: 69

Text #6

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3033. Min Act: -0.0000

Data Index: 1067066 (The Pile)

Max Activating Token Index: 942

Text #7

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3166. Min Act: -0.0000

Data Index: 606169 (The Pile)

Max Activating Token Index: 273

Text #8

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3017. Min Act: -0.0000

Data Index: 1409097 (The Pile)

Max Activating Token Index: 369

Text #9

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2972. Min Act: -0.0000

Data Index: 54396 (The Pile)

Max Activating Token Index: 908

Text #10

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3053. Min Act: -0.0000

Data Index: 68947 (The Pile)

Max Activating Token Index: 92

Text #11

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1380599 (The Pile)

Max Activating Token Index: 694

Text #12

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1510925 (The Pile)

Max Activating Token Index: 288

Text #13

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2909. Min Act: -0.0000

Data Index: 1879561 (The Pile)

Max Activating Token Index: 750

Text #14

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3087. Min Act: -0.0000

Data Index: 818876 (The Pile)

Max Activating Token Index: 375

Text #15

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3077. Min Act: -0.0000

Data Index: 1683 (The Pile)

Max Activating Token Index: 374

Text #16

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2957. Min Act: -0.0000

Data Index: 1544509 (The Pile)

Max Activating Token Index: 58

Text #17

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1295115 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2951. Min Act: -0.0000

Data Index: 1854275 (The Pile)

Max Activating Token Index: 547

Text #19

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3039. Min Act: -0.0000

Data Index: 1423939 (The Pile)

Max Activating Token Index: 875